On Thu, Dec 5, 2019 at 9:06 AM Sergey Senozhatsky <sergey.senozhatsky.work@xxxxxxxxx> wrote: > > On (19/12/04 14:11), Colin King wrote: > [..] > > diff --git a/drivers/staging/media/meson/vdec/vdec.c b/drivers/staging/media/meson/vdec/vdec.c > > index 0a1a04fd5d13..8dd1396909d7 100644 > > --- a/drivers/staging/media/meson/vdec/vdec.c > > +++ b/drivers/staging/media/meson/vdec/vdec.c > > @@ -133,6 +133,8 @@ vdec_queue_recycle(struct amvdec_session *sess, struct vb2_buffer *vb) > > struct amvdec_buffer *new_buf; > > > > new_buf = kmalloc(sizeof(*new_buf), GFP_KERNEL); > > + if (!new_buf) > > + return; > > new_buf->vb = vb; Thanks for the patch Colin. > > So the buffer is not getting recycled? IOW is leaked? > > -ss The "recycle" mechanism in the meson vdec is a way to tell the firmware that "hey, both userspace and kernel are done using this buffer, you can start using it again". Not queuing it for recycling means that the firmware won't use this buffer again, it's not desirable of course, but if there is no memory left to allocate a simple list element then there are bigger problems at hand. Either way, failing this allocation and returning instantly doesn't leak anything or do any damage kernel-side.
